Toward a Taxonomy and Computational Models of Abnormalities in Images

12/04/2015
by   Babak Saleh, et al.
0

The human visual system can spot an abnormal image, and reason about what makes it strange. This task has not received enough attention in computer vision. In this paper we study various types of atypicalities in images in a more comprehensive way than has been done before. We propose a new dataset of abnormal images showing a wide range of atypicalities. We design human subject experiments to discover a coarse taxonomy of the reasons for abnormality. Our experiments reveal three major categories of abnormality: object-centric, scene-centric, and contextual. Based on this taxonomy, we propose a comprehensive computational model that can predict all different types of abnormality in images and outperform prior arts in abnormality recognition.

READ FULL TEXT

page 1

page 3

page 8

research
11/09/2014

Abnormal Object Recognition: A Comprehensive Study

When describing images, humans tend not to talk about the obvious, but r...
research
05/12/2018

Exploring object-centric and scene-centric CNN features and their complementarity for human rights violations recognition in images

Identifying potential abuses of human rights through imagery is a novel ...
research
05/19/2023

TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks

While LLMs have shown great success in understanding and generating text...
research
03/06/2023

UniHCP: A Unified Model for Human-Centric Perceptions

Human-centric perceptions (e.g., pose estimation, human parsing, pedestr...
research
11/11/2020

Intentonomy: a Dataset and Study towards Human Intent Understanding

An image is worth a thousand words, conveying information that goes beyo...
research
10/20/2022

MovieCLIP: Visual Scene Recognition in Movies

Longform media such as movies have complex narrative structures, with ev...
research
11/16/2021

CAR – Cityscapes Attributes Recognition A Multi-category Attributes Dataset for Autonomous Vehicles

Self-driving vehicles are the future of transportation. With current adv...

Please sign up or login with your details

Forgot password? Click here to reset